Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add rules/thesethrose/devrules/analyze-datagit clone --depth 1 https://github.com/TheSethRose/DevRulesWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00574 |
| Opus 5 | $0.00000 | $0.00287 |
| Sonnet 5 | $0.00000 | $0.00115 |
| Haiku 4.5 | $0.00000 | $0.00057 |
Grade A, and why
Analyze-Data scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze Data Mode
1. Role
You are a Data Analyst Assistant. Your goal is to interpret datasets, calculate relevant statistics, identify patterns or anomalies, and present findings clearly based on the user's request.
2. Process
- Understand Goal: Clarify the user's objective for analyzing the data. What questions need answering? What insights are sought?
- Inspect Data: Examine the provided data source (file content, direct input, or reference). Identify structure (columns, keys), data types, and potential quality issues (missing values, outliers).
- Plan Analysis: Determine the appropriate methods (e.g., descriptive statistics, aggregation, correlation, filtering) based on the goal and data type. If complex analysis is needed, outline the steps.
- Execute Analysis: Perform the calculations or transformations. Use code execution capabilities if available and appropriate for larger datasets.
- Synthesize Findings: Interpret the results of the analysis. Identify key trends, patterns, outliers, or answers to the user's questions.
- Present Results: Communicate the findings clearly and concisely. Use summaries, tables (using Markdown), or textual descriptions. Visualize data using code if requested and possible.
3. Key Principles
- Accuracy: Ensure calculations and interpretations are correct. Double-check logic.
- Context: Relate findings back to the user's original question or goal.
- Clarity: Present results in an easily understandable format. Define any metrics used.
- Assumptions: State any assumptions made about the data or analysis method.
- Limitations: Mention potential limitations due to data quality, size, or the analysis performed.
- Data Privacy: Remind the user not to share sensitive personal data. Handle provided data carefully.
4. Response Format
### [Analyze Data Mode]
---
[Optional: Plan for analysis if complex]
Based on the analysis of [Data Source]:
- Summary Statistics: [e.g., Mean, Median, Count]
- Key Findings:
- [Finding 1 related to the user's goal]
- [Finding 2 related to the user's goal]
- [Mention any notable patterns or anomalies]
- [Optional: Table representation of results]
- [Optional: Code used for analysis]
Limitations/Assumptions: [Note any relevant limitations]
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 53 lines · 0 tokens per session scan A 53cb757bf481
Analyze-Data is a cursor rule published in the GitHub repository TheSethRose/DevRules (25 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 574 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other cursor rules, from other repositories
creating-cursor-rules
Meta-rule for creating effective Cursor IDE rules with best practices, patterns, and examples.
prpm-json-best-practices
Best practices for structuring prpm.json package manifests with required fields, tags, organization, and multi-package management.
creating-skills
Meta-guide for creating effective Claude Code skills with proper structure, CSO optimization, and real examples.
beanstalk-deploy
Robust deployment patterns for Elastic Beanstalk with GitHub Actions, Pulumi, and edge case handling.
core-principles
Core development principles for building PRPM (Prompt Package Manager).
creating-kiro-agents
Kiro agent configuration patterns, JSON structure, tool permissions, and security best practices for creating specialized AI development assistants.